Applying deep-learning data analytics to studying and mapping gene sequences, also known as genomics, can result in astonishing feats that were not possible a few years back. A doctor can spot life-threatening diseases in very early stages through genome analytics. Farmers can use it to boost up crop yields. Nutrition can be able to formulate precise diets fashioned to a person’s needs. But privacy rights remains a problem.
Pharmaceutical, healthcare and agricultural industries seek services of data analytics specialists for studying a massive amount of genome data to have insights that will have a revolutionary effect on multiple aspects of research and development. But they do it while being careful of potential privacy violations.
Soon-to-be analytics candidates, who will have an MS in Business Data Analyticsare all set for a lucrative career in the field of genome analytics.
Massive benefits of Genome Analytics:
One should have a grasp of how genome analytics works before moving on to understand the role of deep-learning intelligence analysis in genomics.
MahniGhorashi and Gaurav Garg explain in a Tech Crunch’s article titled as ‘The Genomics Intelligence Revolution’ that Genomics analytics occurs in three stages:
- Primary–Sequencers do some raw chemistry as well as initial conversion of an available physical sample into raw data sequence.
- Secondary –Base pairs from the sequencer, previously out of order, are put together in correct order through a compute-intensive process.
- Tertiary –Meaning is extracted from genetic data that turns into an analytics-fueled applied science, capable of amazing discoveries such as matching particular genetic mutations with known diseases.
Ghorashi and Garg explain add, ‘We can extract meaning from an individual’s genetic data by comparing it to other reference genomes. And the more reference genomes we have to work with the better our software and our processes can become. This is why plans to build giant databases of genetic data are fundamental to the future of this work.’
With analysis of mega databases of genetic data, fields such as nutritional genomics and nurtigenomics seem to be materializing in the near future. Joe Schwartz, business expert, in his Science Daily’s article titled as ‘Healthy Diet? That Depends On Your Genes’writes,‘Based on one’s ancestry, clinicians may one day tailor each person’s diet to her or his genome to improve health and prevent diseases.’
Schwartz’s article details experiments on the varying nutritional requirements of people who had different ancestral history to shed more light on his point. For example, FADSI gene – common in people having European ancestors- developed after several years of vegetarian farming.It has a role in biosynthesis of polyunsaturated fatty acids. On the other hand, an analyses of a hunter-gatherer DNA exposed an opposite version of the same gene.
With the evolution ofnurtigenomics, a valuable insight into an individual’s nutritional health will be available for clinicians, nutritionists, nutraceutical companies and food manufacturers. Agricultural industry may also benefit from it.
Dr. Sherri Brown a strategist from Montano, inarticle titled as ‘Plant Science AndAgri-Genomics: The Importance Of Collaboration’writes, ‘Genome-editing techniques will drive new improvements in agriculture through a broad range of solutions that could help farmers deliver better harvests. In plant breeding, genome-editing technology could enable plant breeders to deliver better hybrids and varieties more efficiently, allowing them to combine specific plant characteristics in initial crosses between plants, as opposed to breeding for such combinations over multiple years.”
The Privacy Issue:
No one can deny benefits of genome analytics.But a real genetic sequencing of humans on a mega scale is required to create giant genome datasets for the use of deep learning algorithms for analyses and comparison purposes.
AncestryDNA and 23andMe offer gene-sequencing services for $100. The price was tens of millions of dollars just a few years back. Anyone who desires to learn about his or her genetic background can benefit from it. Each client receives results that show his ethnic background and ancestry. Add a little more money and they will also provide you your health information.
However, genetic sequencing companies retain this genetic data even after they have provided you the results. They have freedom to sell this data to third-party pharmaceutical and medical companies. And here comes the privacy issue.
In their paper titled as ‘Exploring The Cancer Genome’published on the National Cancer Institute’s website Shannon Behrman, PhD and Jessica Mazerik, PhD, write,‘Another enormous challenge in genome research is generating and sharing data that result in impactful discoveries without compromising the confidentiality and rights of patients. This issue is further complicated because each country has its own laws for patient protection, informed consent, and institutional review board (IRB) approval processes.
[The International Cancer Genome Consortium] has taken into account these legal and regulatory differences and developed suggested guidelines for informed consent, data access, and ethical oversight that minimize the risk of individual patient identification without impeding important research opportunities.’
Health Insurance Portability and Accountability Act (HIPAA) established a privacy rule that requires that healthcare data which can compromise identity of a patient or a client must be deleted or encrypted through de-identification or anonymyzation.Usually the information contains social security numbers, account numbers, names, phone numbers, addresses or anything else that helps discover a person’s identity.
But the problem with de-identification is that genetic data itself carries a person’s identity. There are programs available that use a person’s genetic information to build a model of his or her face. The results are amazingly and incredibly accurate when they are compared with the person’s actual face.
Consultant Barbara L. Filkins, et al., in her article titled as ‘Privacy And Security In The Era Of Digital Health: What Should Translational Researchers Know And Do About It?’published on the National Institutes of Health government website writes, ‘Regardless of the methods, there is always a possibility of re-identification. Identifiable markers can be used to determine the presence of an individual in a dataset, even without explicit personal information or when the genomic data has been aggregated.’
It means that genetic data can be re-identified by comparing the de-identified data with public datasets as well as other information sources that are accessible. Genomics analytics organizations are trying to find a way to forsee and prevent these threats so that business of genomics may go on and keep bringing productive insights for researchers and developers.
Master Degree in Business Data Analytics by Maryville University
Maryville University’s online Master’s of Science in Business Data Analytics degree fulfills the increasing demand for business analytics experts. After graduation students will be fully equipped to join workforce as data analyst, statistician, data scientist or a genomics analytics specialist.
At Maryville University students are coached in a way so that they could handle datasets, monetize data, mastermind multiple infrastructure and make decisions on the basis of valuable analytics insights. Graduates will trained in such a way that they could juxtapose business operational data and latest analytical tools, and becoming indispensable to employers.